© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12759
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and values in biological contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     useAppContext
    -0.59
    ONESIA
    -0.55
    (");
    -0.54
     createState
    -0.54
    yarnpkg
    -0.54
    InitVars
    -0.54
     estekak
    -0.53
    npmjs
    -0.52
     nahilalakip
    -0.52
    :])
    -0.52
    POSITIVE LOGITS
     przecież
    0.65
    věř
    0.59
     posterity
    0.57
     extérieures
    0.56
    Must
    0.54
     scolaire
    0.54
     vezes
    0.53
     Título
    0.52
     schoolmaster
    0.52
     éduc
    0.51
    Activations Density 0.243%

    No Known Activations